{ "epoch": 0.9997172745264349, "eval_logits/chosen": -0.925058126449585, "eval_logits/rejected": -0.9405221939086914, "eval_logps/chosen": -4.356727600097656, "eval_logps/rejected": -5.03577995300293, "eval_loss": 2.5820231437683105, "eval_rewards/accuracies": 0.7914438247680664, "eval_rewards/chosen": -43.56727981567383, "eval_rewards/margins": 6.790517807006836, "eval_rewards/rejected": -50.35779571533203, "eval_runtime": 50.3639, "eval_samples_per_second": 59.15, "eval_steps_per_second": 3.713, "total_flos": 134366991482880.0, "train_loss": 3.371998559026157, "train_runtime": 3776.6556, "train_samples_per_second": 14.984, "train_steps_per_second": 0.117 }